© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 58699
    Prev
    Next
    INDEX
    Explanations

    code or data

    np_max-act · gemini-2.0-flash

    phrases or questions related to the correct usage of specific terms like "respectively."

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects individual items in paired lists or sequences—especially variable or element names (like “a,” “b,” “c,” “d,” etc.)—typically those appearing just before “respectively.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     col
    -0.07
    -global
    -0.06
    监督
    -0.06
     Monsters
    -0.06
    steel
    -0.06
     humiliation
    -0.06
    -native
    -0.06
     Επι
    -0.06
    (shift
    -0.06
    -print
    -0.06
    POSITIVE LOGITS
    itori
    0.07
    _ELEM
    0.06
    Laura
    0.06
     SimpleDateFormat
    0.06
    NASDAQ
    0.06
     nigeria
    0.06
     Laura
    0.06
    ivial
    0.06
    IBOutlet
    0.06
     Reflect
    0.06
    Activations Density 0.116%

    No Known Activations